作者位次 #4/5ACL 2026Poster· Natural Language Processing
Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs
Haoyue Liu · Zhichao Wang · Yongxin Guo · Haoran Shou · Xiaoying Tang
摘要
Automated prompt optimization is crucial for eliciting reliable reasoning from large language models (LLMs), yet most API-only prompt optimizers iteratively edit monolithic prompts, coupling components and obscuring credit assignment, limiting controllability, and wasting tokens. We propose Adapt...